> Hand-written real-mode 8086. No C, no linker, no runtime library.
More like hand-prompted...
back
6 comments
From the landing page:
> 66,183 lines of hand-written real-mode assembly
Goes to the github - contributers jggonz and CLAUDE. The README.md doubles down on this at the bottom with the license.
> Everything here is hand-written; no third-party code is vendored into the OS, so the whole tree is covered by that one license.
That's what happens when you let an LLM write your ad-copy...
It can't be written by LLM -- the human author has claimed copyright
> there is no value in being a Public-Domain-Dumping-Ground.
First of all, isn't that the entire point of the Internet Archive? Sounds pretty valuable to me.
Second, doesn't the same issue effectively apply to everything written with the BSD or MIT license? I'm not sure I understand the point though, so I'm probably missing something.
Did you believe that the Internet Archive hosts nothing but PD content?
The Internet Archive has lots of PD books and other works that have been scanned in. But the Internet Archive's web pages are all copyrighted. Only a small percentage of anything on the Internet is PD. All those news articles that HN bypasses paywall? Piracy of copyright.
How do you think the IA got in legal trouble during the pandemic lockdowns?
There are instances of purely PD archives: librivox.org and gutenberg.org. Their mandate means everything is PD, whether it was PD to begin, or whether it is novel work by modern creators. The archives are sustained by their donors and volunteers, who are scanning these works, fixing up the OCR, recording audiobooks, and otherwise donating their time, talent, and treasure to building the archives. Perhaps both are obsolete by now.
Everything written in BSD and MIT license is copyrighted. Copyright may be assigned, dual-license status may exist, non-exclusive rights may be assigned. None of this applies with purely PD works.
I stated no mere opinions, and I made no novel predictions, but I gave observations of current practices. The only prediction is that these two practices expand and escalate for as long as LLMs' legal status remains this way.
A BSD or MIT (or any other) license doesn’t remove copyright. For example, copyright reserves the author the right to also release the work under a different license in the future. AI output doesn’t have such associated rights.
You're not missing anything. I think this is a person trying to speak their opinion into fact by quoting themselves.
1. The copyright claim is valid in places where LLM output is always covered by copyright.
2. It may be valid in places where sufficient human contribution makes AI code covered by copyright.
Even if it is not covered by copyright everywhere, it has a significant effect. If something is covered by copyright in some countries but not others its cannot be globally distributed without a license.
> 1. The copyright claim is valid in places where LLM output is always covered by copyright.
Actually not: the copyright claim would be particularly egregious in, e.g. the UK, because if the publisher has not even acknowledged or attributed contributions to Claude, then Claude's copyright is infringed, and the publisher could be liable for fraud on top of that.
And to address your second point: if the publisher claims 100% ownership, authorship and copyright, then who can even determine the amount of LLM-authored code? Something must come out in depositions or the courtroom about how much Claude committed, and how much was by humans, because in this case in this thread, the publisher has claimed 100% human authorship.
> Actually not: the copyright claim would be particularly egregious in, e.g. the UK, because if the publisher has not even acknowledged or attributed contributions to Claude, then Claude's copyright is infringed
I think you are wrong there. Claude cannot hold a copyright. Anthropic might but I think that is a misinterpretation of the law. The government thinks the person who prompted holds the copyright: "In the case of a general purpose AI which generates output in response to a user prompt, the “author” will usually be the person who inputted the prompt." :
https://www.gov.uk/government/publications/report-and-impact...
Are you saying that this is wrong and the developer of the LLM holds the copyright on all its output?
> And to address your second point: if the publisher claims 100% ownership, authorship and copyright, then who can even determine the amount of LLM-authored code?
Does it matter? Either the human author/prompter holds the copyright, or no one does. They just need to show that they have made a sufficient contribution to hold the copyright. Commits and prompt history would be a good start.
"Author" of os8088 here. You're right, it's hand-prompted.
Claude's Opus and Fable have done a really great job helping me and another contributor shape this operating system. It's been a really interesting way to learn about the different techniques that other operating systems have used to get the performance we saw in LisaOS, MacOS, Windows, GEOS, etc... performance at 640x480 on an XT class machine is tricky! Also, the 64KB segment limitations were very interesting to overcome!
One thing is where you learn through llm and then apply this knowledge, write asm the way humans do, another is letting Claude generate everything.
Did you ask Claude to write this comment too?
lol, so disappointing to see the attacks when I'm just having some fun.
It would probably had been fine had you just not put the "hand written" part.
Yes, agree. I laughed at that when I first saw it last week. I went ahead and cleared all that up on the homepage and the README now.
You haven’t even wrote readme yourself?
Funnily enough he removed hand written part also by Claude. Just wow.
Stop calling it "Mac-like" and the project will live longer
No, please keep on track. "Mac-like" is a perfect fit for the "Daddy, what's (a) computer/programming?" vibe crowd.
Even The Company itself thinks so, as evidenced by relevant advertisements of the not too distant past. :)
And LLMs are still confidently bullshitting:
> Everything after that is the interface you remember from a 1984 Macintosh: […] and a dock along the bottom with one tile per running program.
In that case I look forward to seeing OS X’s Aqua ported to the IBM PS/2.
If we’re going to be really pedantic, there was no “System 1” as TFA says as well anyway - I don’t think there was an actual “version 1” of the System File version 1, and most of the routines at that point were in ROM.
But an LLM would have caught that. Signs of a human touch?
> I don’t think there was an actual “version 1” of the System File version 1
There definitely was. https://en.wikipedia.org/wiki/System_1:
“The Macintosh "System 1" is the first major release of the classic Mac OS operating system. It was developed for the Motorola 68000 microprocessor. System 1 was released on January 24, 1984, along with the Macintosh 128K, the first in the Macintosh family of personal computers. It received one update, "System 1.1" on December 29, 1984, before being succeeded by System 2”
That page doesn’t mention it but I think the original Mac shipped with a 0.97 or 0.98 version.
Watch out for the scare quotes though - it actually did give me the opportunity to check: Finder 1.0 shipped with System file .97, and Finder 1.1 shipped with System file 1.1g - and it looks like “System Software 1.0” actually refers to Finder 5.2/System file 3.1!
https://en.wikipedia.org/wiki/Classic_Mac_OS#System_1,_2,_3,...
In that case I look forward to seeing OS X’s Aqua ported to the IBM PS/2.
If this project is any indication, AI can definitely make that happen too.
I’ve got nothing against AI-written code
But if people are going to post it on HN, they should consider at least writing the README / main page of their website by hand
It is nice to hear the human authorial voice, at least sometimes
I agree. We've just been spending more time on the operating system than the homepage. I'm making some updates, but it's still all going to be written "through" AI for now.
but it's still all going to be written "through" AI for now.
Why the hedge? Why not just be honest say it was written "by" AI, since it was?
You sound like when a company pays to sponsor another company's work, and they get a "powered by" tagline, even though they contributed no actual power/effort. "The Flatulence 100 Bicycle Race powered by Zyzzyz Bank."
Why, are you incapable of writing three paragraphs of text to present your work?
I'm surprised Claude is actually decent at real-mode Asm, but maybe there was a lot of attempts and guidance by the human.
Ive been throwing z80, 6502, 68000, 8086, i386 and x86_64 asm at it lately. Haven't seen it get stuck on any of them.
Do you think the low-level nature of ASM contribute to how successful the LLMs are with it?
I think also that a large/smart/fast LLM can automate testing things with QEMU for at least moderately common architectures like motorola 68000, throw code at it rapidly and try different iterations.
github ?
The assembly really, really hurts to read.
In what way?
It looks much closer to real human-written Asm than compiler output, which is itself a big win. No stupid calling conventions or obvious bloat. The unmistakably bloated inefficiency of "compiler slop" (that term wasn't used at the time, but those who lived through that Asm vs HLL era on the PC will know exactly what I'm talking about) is not present. I can always spot immediate optimisation opportunities with compiler output, but at a quick glance, not in this code.
...and now I have the idea of getting AI to decompile some existing binaries and then have it optimise/rewrite in the style of human-written Asm... run something like Windows XP or even 11 through it and see if it can be optimised down to a tiny fraction of its current resource usage.
Random inconsistencies such as using push/pop for individual registers instead of pusha/popa for space constrained bits or setting the same register to the same value twice in a row.
Not to even mention that random WORDS are capitalized for some REASON as well.
pusha/popa for space constrained bits
Those instructions were introduced in the '186/8 but this project targets the 8086/8088.
Not sure what the point is having AI write asm when it could write C, which a compiler could likely optimize better than AI.